Triple
T38662678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Presidential Office (Republic of China) |
E940373
|
entity |
| Predicate | usedAsPresidentialOfficeSince |
P144818
|
FINISHED |
| Object | 1950 |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 1950 | Statement: [Presidential Office (Republic of China), usedAsPresidentialOfficeSince, 1950]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsPresidentialOfficeSince Context triple: [Presidential Office (Republic of China), usedAsPresidentialOfficeSince, 1950]
-
A.
presidentSince
Indicates that one entity has held the office of president of another entity starting from a specified point in time.
-
B.
tookOfficeAfter
Indicates that one entity assumed an official position or office at a later time than another entity did.
-
C.
presidentAtStartOfTerm
Indicates that the subject was the president holding office at the beginning of the specified term or period.
-
D.
presidencyOf
Indicates the relationship in which a person holds or held the office of president of a particular organization, country, or entity.
-
E.
timePeriodOfUseAsPresidentialOffice
chosen
Indicates the span of time during which a particular place or building was used as a presidential office.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76edfde348190bf6529d9f49ecd62 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff370698ec81909bb1596d7d4112ba |
completed | May 9, 2026, 1:30 p.m. |
| PD | Predicate disambiguation | batch_69ff3699b6288190b564839cb05f5cf6 |
completed | May 9, 2026, 1:28 p.m. |
Created at: May 3, 2026, 4:33 p.m.